Unbounded Prometheus label growth in vLLM enables denial of service
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Partial Red Hat: 3 without a fix
Attack profile from CVSS 3.1 · NVD. Fix status from CNA and Red Hat. Impact type from CWE-400.
Summary
vLLM before 0.30.0 has an uncontrolled resource consumption flaw in the Rust frontend's track_http_metrics middleware (CWE-400). It records the raw HTTP method token as a Prometheus label, so an unauthenticated remote attacker can send unique method tokens to unguarded routes such as /tokenize. Each new token creates counter and histogram label sets that grow memory use and the /metrics response until the service or monitoring path is exhausted. A public exploit is linked in the references.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
Description from the CNA
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| vllm-project | vllm | before 0.30.0 | 0.30.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected before 0.30.0 Fixed in 0.30.0 Patch available CNA
Remediation
Upgrade vLLM to version 0.30.0, which fixes the flaw. Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI) are listed as affected without a fix, and Red Hat's plan for them is none available.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
- Fix · CNA vllm (vllm-project) Fixed in 0.30.0
Vendor assessments
Red Hat
Red Hat rating: Moderate. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat AI Inference Server | Affected | No fix yet: Fix deferred |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix yet: Fix deferred |
| Red Hat OpenShift AI (RHOAI) | Affected | No fix yet: Fix deferred |
Timeline
- 2026-10-06 Threatist record created from CVE-2026-105759
- 2026-10-06 Affected versions changed · Red Hat
- 2026-10-06 CVSS score added · Red Hat
- 2026-10-06 CISA SSVC decision points changed
- 2026-10-18 CVSS score added · NVD
- 2026-10-18 Priority changed: MEDIUM → HIGH
References
More vllm-project vulnerabilities
- TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
- TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
- TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
- TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
- TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
- TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
Sources
- CVE-2026-105759 · CVE Program
- CVE-2026-105759 · NVD
- FIRST EPSS
- CVE-2026-105759 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences